🔥CDIoU and CDIoU loss is like a convenient plug-in that can be used in multiple models. CDIoU and CDIoU loss have different excellent performances in several models such as Faster R-CNN, YOLOv4, RetinaNet and . There is a maximum AP improvement of 1.9% and an average AP of 0.8% improvement on MS COCO dataset, compared to traditional evaluation-feedback modules. Here we just use as an example to illustrate the code.
In the paper, the calculation of diou is the distance between the predicted frame and the four vertices of the real frame divided by four times the diagonal distance, but why in the code, there are only two vertices divided by twice the diagonal distance distance?
In the paper, the calculation of diou is the distance between the predicted frame and the four vertices of the real frame divided by four times the diagonal distance, but why in the code, there are only two vertices divided by twice the diagonal distance distance?